Skip to content

All pages

Magnitude

Open source inference server that picks local models to fit your hardware

AI14d ago
Category
AI
Website
github.com
Language
English
Listed
14d ago
Forks
352

magnitudedev/magnitude ↗, TypeScript, Apache-2.0, Last commit 23h ago

Magnitude profiles the machine it is installed on, works out which local models actually fit, then downloads, tunes, and serves them. The point is that you do not pick the model by guesswork.

It plugs into agents you may already be running, including Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline, and ships a built-in harness if you are not using any of them. Because inference stays on your own hardware, it runs offline and nothing leaves the machine. The project is Apache 2.0 licensed and installs through its npm CLI.

Like this product?